Road Closure Detection based upon Multi-feature Fusion

Abstract

Delayed and missed detection of road closure brings a great influence on the quality of the digital map. The existing solutions using trajectory data aim to identify the closed roads according to the drastic drop property in traffic flow. But in actual applications, such methods may lead to the misidentification of a traffic jam as closure, and cannot detect some events like one side closure of two-way road and the closure in the middle of the road. With the occurrence of road closure, there are variations of turning volume of neighboring roads and the increment of U-turn frequency on the closed roads besides the drastic drop of traffic flow. In this paper, we present a high-efficiency road closure detection framework based upon multi-feature fusion, called RCDM. It consists of an off-line road closure feature modeling part and an online identification part. In the off-line phase, we first partition the road network into grids, and then extract road closure features of grids and those of roads from historical data. In the online phase, on the basis of the predictions for road closure features, we screen out closed grid candidates in terms of traffic flow plunge property and further pinpoint the closed road sections according to turning behavior variations of roads. Extensive experimental results on three real data sets from Chengdu, Shanghai and Beijing validate that our method has higher detection accuracy and efficiency compared with the existing methods.